Merge pull request #43 from 4dn-dcic/s3zip

s3_util unzip function can take file suffices instead of full file name

dcicutils/_version.py

@@ -1,4 +1,4 @@
 """Version information."""
 
 # The following line *must* be the last in the module, exactly as formatted:
-__version__ = "0.7.5"
+__version__ = "0.7.6"

dcicutils/s3_utils.py

@@ -191,10 +191,7 @@ def read_s3_zipfile(self, s3key, files_to_extract):
                 ret_files[name] = zipstream.open(zipped_filename).read()
         return ret_files
 
-    def unzip_s3_to_s3(self, zipped_s3key, dest_dir, retfile_names=None, acl=None):
-        if retfile_names is None:
-            retfile_names = []
-
+    def unzip_s3_to_s3(self, zipped_s3key, dest_dir, acl=None):
         if not dest_dir.endswith('/'):
             dest_dir += '/'
 
@@ -218,9 +215,8 @@ def unzip_s3_to_s3(self, zipped_s3key, dest_dir, retfile_names=None, acl=None):
                 # files twice that we want to further interogate
                 the_file = zipstream.open(file_name, 'r').read()
                 file_to_find = file_name.split('/')[-1]
-                if file_to_find in retfile_names:
-                    ret_files[file_to_find] = {'s3key': s3_key,
-                                               'data': the_file}
+                ret_files[file_to_find] = {'s3key': s3_key,
+                                           'data': the_file}
                 self.s3_put(the_file, s3_file_name, acl=acl)
 
         return ret_files

test/test_s3_utils.py

@@ -93,9 +93,7 @@ def test_unzip_s3_to_s3(integrated_s3_info):
     assert [] == objs.get('Contents', [])
 
     # now copy to that dir we just deleted
-    retfile_list = ['summary.txt', 'fastqc_data.txt', 'fastqc_report.html']
-    ret_files = integrated_s3_info['s3Obj'].unzip_s3_to_s3(filename, prefix, retfile_list)
-    assert 3 == len(ret_files.keys())
+    ret_files = integrated_s3_info['s3Obj'].unzip_s3_to_s3(filename, prefix)
     assert ret_files['fastqc_report.html']['s3key'].startswith("https://s3.amazonaws.com")
 
     objs = integrated_s3_info['s3Obj'].s3_read_dir(prefix)